Recognition of Propaganda Techniques in Newspaper Texts: Fusion
of Content and Style Analysis

J 2024

Recognition of Propaganda Techniques in Newspaper Texts: Fusion of Content and Style Analysis

HORÁK, Aleš, Radoslav SABOL, Ondřej HERMAN a Vít BAISA

Základní údaje

Originální název

Recognition of Propaganda Techniques in Newspaper Texts: Fusion of Content and Style Analysis

Autoři

HORÁK, Aleš (203 Česká republika, garant, domácí), Radoslav SABOL (703 Slovensko, domácí), Ondřej HERMAN (203 Česká republika, domácí) a Vít BAISA (203 Česká republika, domácí)

Vydání

Expert Systems with Applications, Elsevier, 2024, 0957-4174

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

10200 1.2 Computer and information sciences

Stát vydavatele

Spojené státy

Utajení

není předmětem státního či obchodního tajemství

Odkazy

URL

Impakt faktor

Impact factor: 8.500 v roce 2022

Organizační jednotka

Fakulta informatiky

DOI

http://dx.doi.org/10.1016/j.eswa.2024.124085

UT WoS

001235661700001

Klíčová slova anglicky

propaganda; disinformation; manipulative techniques; text style analysis; benchmark dataset

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 14. 9. 2024 10:14, doc. RNDr. Aleš Horák, Ph.D.

Anotace

V originále

Public texts aiming at reader manipulation for propaganda or disinformation purposes pose a significant threat to society. The ability to detect the presence of a specific manipulative technique in a text offers an informed warning to readers and guides them to carefully judge the actual statement. In this article, we address the problem of developing new models capable of analyzing newspaper articles for propagandistic features. We introduce a new large dataset of manipulative techniques obtained via gathering and human annotation of 8,646 newspaper articles in Czech, which represents one of the former Soviet influence area languages. The dataset allows both to train new methods to recognize propaganda and disinformation and offer a general comparable benchmark for the techniques. We evaluate the dataset against selected state-of-the-art machine learning approaches to provide high-performing baselines for detecting seventeen annotated manipulative techniques. We also present thorough measurements of inter-annotator agreements that approximate the difficulty level of each of the attributes. As a new finding, we propose a set of text style analysis features that lean on the assumption that each manipulation leads to a specific style pattern. We show that the style analysis improves the detection results for most of the manipulative techniques. The viability of the approach is also confirmed on the well-known QProp propaganda dataset, providing new state-of-the-art results.

Návaznosti

LM2023062, projekt VaV

Název: Digitální výzkumná infrastruktura pro jazykové technologie, umění a humanitní vědy

Investor: Ministerstvo školství, mládeže a tělovýchovy ČR, LINDAT/CLARIAH-CZ - Digitální výzkumná infrastruktura pro jazykové technologie, umění a humanitní vědy

Citovat

HORÁK, Aleš, Radoslav SABOL, Ondřej HERMAN a Vít BAISA. Recognition of Propaganda Techniques in Newspaper Texts: Fusion of Content and Style Analysis. Expert Systems with Applications. Elsevier, 2024, roč. 2024, č. 251, s. 124085-124095. ISSN 0957-4174. Dostupné z: https://dx.doi.org/10.1016/j.eswa.2024.124085.

@article{2395577,
   author = {Horák, Aleš and Sabol, Radoslav and Herman, Ondřej and Baisa, Vít},
   article_number = {251},
   doi = {http://dx.doi.org/10.1016/j.eswa.2024.124085},
   keywords = {propaganda; disinformation; manipulative techniques; text style analysis; benchmark dataset},
   language = {eng},
   issn = {0957-4174},
   journal = {Expert Systems with Applications},
   title = {Recognition of Propaganda Techniques in Newspaper Texts: Fusion of Content and Style Analysis},
   url = {https://doi.org/10.1016/j.eswa.2024.124085},
   volume = {2024},
   year = {2024}
}

TY  - JOUR
ID  - 2395577
AU  - Horák, Aleš - Sabol, Radoslav - Herman, Ondřej - Baisa, Vít
PY  - 2024
TI  - Recognition of Propaganda Techniques in Newspaper Texts: Fusion of Content and Style Analysis
JF  - Expert Systems with Applications
VL  - 2024
IS  - 251
SP  - 124085
EP  - 124085
PB  - Elsevier
SN  - 09574174
KW  - propaganda
KW  - disinformation
KW  - manipulative techniques
KW  - text style analysis
KW  - benchmark dataset
UR  - https://doi.org/10.1016/j.eswa.2024.124085
N2  - Public texts aiming at reader manipulation for propaganda or disinformation purposes pose a significant threat to society. The ability to detect the presence of a specific manipulative technique in a text offers an informed warning to readers and guides them to carefully judge the actual statement. In this article, we address the problem of developing new models capable of analyzing newspaper articles for propagandistic features. We introduce a new large dataset of manipulative techniques obtained via gathering and human annotation of 8,646 newspaper articles in Czech, which represents one of the former Soviet influence area languages. The dataset allows both to train new methods to recognize propaganda and disinformation and offer a general comparable benchmark for the techniques. We evaluate the dataset against selected state-of-the-art machine learning approaches to provide high-performing baselines for detecting seventeen annotated manipulative techniques. We also present thorough measurements of inter-annotator agreements that approximate the difficulty level of each of the attributes. As a new finding, we propose a set of text style analysis features that lean on the assumption that each manipulation leads to a specific style pattern. We show that the style analysis improves the detection results for most of the manipulative techniques. The viability of the approach is also confirmed on the well-known QProp propaganda dataset, providing new state-of-the-art results.
ER  -

HORÁK, Aleš, Radoslav SABOL, Ondřej HERMAN a Vít BAISA. Recognition of Propaganda Techniques in Newspaper Texts: Fusion of Content and Style Analysis. \textit{Expert Systems with Applications}. Elsevier, 2024, roč.~2024, č.~251, s.~124085-124095. ISSN~0957-4174. Dostupné z: https://dx.doi.org/10.1016/j.eswa.2024.124085.

Podrobný výpis o publikaci